By introducing two concepts first and second believable levels is proposed a new technique of ensemble forecasting that is applicable to all level stations in the country.

To analyze and compare the advantages and shortcomings of four kinds of intelligence integration technologies,web service/soap is a better technology for intelligence integration,and it has better performances that the other models can not be matched with.

Based on temperature forecast of operational middle-range model of China,operational model of German meteorological administration,operational model of Japan meteorological agency and temperature observations of China,a temperature consensus forecast system is developed through method of artificial neural network.

The outputs of four models(Euler numerical model,neural network model,dynamic statistical model,consensus forecast model) for forecasting precipitation pH from May to September 2005 are analyzed and their effectiveness is compared.